© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11061
    Prev
    Next
    INDEX
    Explanations

    new items or updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    第ä¸Ģ次
    -0.09
    空æ°Ķä¸Ń
    -0.09
    è£ħ
    -0.08
    ĪæĿĥ
    -0.08
    èį£èªī称åı·
    -0.08
    详
    -0.08
    rips
    -0.08
    å¤ļåħĥ
    -0.08
    æĮ½æķij
    -0.08
    kp
    -0.08
    POSITIVE LOGITS
    rama
    0.10
    ãģĮãģĤãģ£ãģŁ
    0.10
    bish
    0.10
    é²ľ
    0.10
    dden
    0.10
    é¢ĸ
    0.09
    æĤ¬
    0.09
    éħ±
    0.09
    大家åĪĨ享
    0.09
    å·²ä¹ħçļĦ
    0.09
    Activations Density 0.043%

    No Known Activations